policy-redraft
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill manages file access through a restricted directory structure at ~/.claude/plugins/config/ and provides clear proposal-only workflows to prevent unintended document modification.
- [PROMPT_INJECTION]: Explicit guardrails are implemented within the skill instructions to prevent the agent from following user prompts that would bypass legal review or automatically apply changes to source documents.
- [COMMAND_EXECUTION]: Tool usage is confined to research and search capabilities for verifying the status of regulatory rules, which does not involve executing arbitrary or untrusted code.
- [DATA_EXFILTRATION]: No evidence of unauthorized network connectivity or exfiltration of sensitive information was found.
Audit Metadata